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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bipolar
    -0.07
     Datos
    -0.07
    Fuck
    -0.07
     Enh
    -0.06
     servicios
    -0.06
     سرم
    -0.06
    Captain
    -0.06
     courageous
    -0.06
     вок
    -0.06
     vrát
    -0.06
    POSITIVE LOGITS
    .visitInsn
    0.07
    .Std
    0.06
    ックス
    0.06
    onomous
    0.06
    onomic
    0.06
     používá
    0.06
    .commands
    0.06
    里的
    0.06
     kad
    0.06
    .byId
    0.06
    Act Density 0.213%

    No Known Activations