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

    Neuronpedia

    INDEX
    Explanations

    recognizable concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     triangle
    0.39
    ocyte
    0.39
     Patch
    0.39
    ɭ
    0.38
    obes
    0.38
     stone
    0.37
     Gopal
    0.37
     kindergarten
    0.37
    AtIndex
    0.37
     Triangle
    0.37
    POSITIVE LOGITS
    みる
    0.41
     fournir
    0.38
     compétition
    0.38
     також
    0.38
    jár
    0.37
    セックス
    0.37
     incorporates
    0.37
     также
    0.37
    真實
    0.36
     зді
    0.36
    Act Density 0.000%

    No Known Activations