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

    Neuronpedia

    INDEX
    Explanations

    Columbia Records

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orben
    0.34
     रझा
    0.33
    czyny
    0.33
    colorChoice
    0.33
    desIP
    0.32
    jeuner
    0.32
    ச்சின்ன
    0.31
    lamualaikum
    0.31
    𒉣
    0.31
    क्शंस
    0.31
    POSITIVE LOGITS
     \
    0.52
     P
    0.39
     IS
    0.39
    $
    0.39
    \
    0.35
    O
    0.35
     W
    0.33
    F
    0.33
     I
    0.33
     N
    0.33
    Act Density 0.000%

    No Known Activations