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

    Neuronpedia

    INDEX
    Explanations

    parsing json code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jí
    0.66
     JBL
    0.64
     J
    0.64
    J
    0.64
    JX
    0.63
     Jia
    0.63
     JI
    0.63
     Juj
    0.62
    jí
    0.62
     j
    0.59
    POSITIVE LOGITS
    json
    0.84
     json
    0.80
    Json
    0.63
     Json
    0.63
    JsonPart
    0.57
     JSON
    0.56
    জন
    0.49
    जनन
    0.47
     sulfonic
    0.47
    Lemon
    0.46
    Act Density 0.038%

    No Known Activations