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

    Neuronpedia

    INDEX
    Explanations

    step-by-step explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ວກ
    0.37
    雰囲
    0.36
     Reed
    0.36
    %(
    0.36
     encaps
    0.35
     thoughts
    0.35
     Balloon
    0.35
     THINK
    0.34
    attempts
    0.34
    なども
    0.34
    POSITIVE LOGITS
     extremos
    0.42
     cathode
    0.40
     mercantil
    0.40
    apanam
    0.39
    رحله
    0.39
     chromatin
    0.39
     thefe
    0.39
    极
    0.38
    <&
    0.38
    kezi
    0.38
    Act Density 0.001%

    No Known Activations