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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tra
    -0.07
     querying
    -0.07
    lb
    -0.07
     yoktu
    -0.07
     seizure
    -0.06
    <N
    -0.06
     whom
    -0.06
    appointment
    -0.06
     occup
    -0.06
    :mm
    -0.06
    POSITIVE LOGITS
     ทำให
    0.06
    �
    0.06
     utils
    0.06
    _imgs
    0.06
    _edit
    0.06
     BAM
    0.06
     тол
    0.06
    ovel
    0.06
     nền
    0.06
    활동
    0.06
    Act Density 0.057%

    No Known Activations