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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Об
    -0.07
     #"
    -0.07
    Ak
    -0.07
     Ak
    -0.07
    атар
    -0.06
    Wer
    -0.06
    .—
    -0.06
    Sel
    -0.06
    ARGER
    -0.06
    genome
    -0.06
    POSITIVE LOGITS
     restitution
    0.07
    LINK
    0.07
    _TAGS
    0.07
     postupně
    0.07
    (boost
    0.06
    ្�
    0.06
     Corp
    0.06
    /></
    0.06
    phthalm
    0.06
     SSP
    0.06
    Act Density 0.016%

    No Known Activations