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

    Neuronpedia

    INDEX
    Explanations

    Code/diagram snippets

    np_max-act · gemini-2.0-flash

    This neuron does not activate for any tokens and thus does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .getEnd
    -0.07
     })(
    -0.07
     Yourself
    -0.06
     bargain
    -0.06
    ...]↵↵
    -0.06
     melted
    -0.06
    erin
    -0.06
    Tax
    -0.06
    Err
    -0.06
    -0.06
    POSITIVE LOGITS
     urlpatterns
    0.06
    osto
    0.06
     biện
    0.06
    IM
    0.06
    �
    0.06
    moid
    0.06
    uristic
    0.06
    (current
    0.06
     ทำ
    0.06
    ublic
    0.06
    Act Density 0.009%

    No Known Activations