Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to debugging and error messages related to identity keys in SSH configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Cryptography-related tokens (DSA, ECDSA, etc.)

    np_acts-logits-general · gemini-2.0-flash

    equations and sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }}^{(
    -0.66
    <bos>
    -0.56
    |}{$
    -0.55
    }}=$
    -0.55
     }}^{\
    -0.53
    ']=$
    -0.52
    (")");
    -0.51
    )}(\
    -0.51
    )}{\
    -0.51
     }_{\
    -0.48
    POSITIVE LOGITS
    :
    1.27
    ::
    0.87
     :
    0.80
    principalColumn
    0.79
    ：
    0.78
    :(
    0.75
    :!
    0.72
    SpringRunner
    0.72
    :=
    0.71
    ∶
    0.71
    Act Density 0.585%

    No Known Activations