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

    Neuronpedia

    INDEX
    Explanations

    Transformations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drowned
    -0.07
     intensely
    -0.07
     Athens
    -0.07
    化
    -0.06
    STOP
    -0.06
    .Adam
    -0.06
    stan
    -0.06
     mature
    -0.06
    etě
    -0.06
     thieves
    -0.06
    POSITIVE LOGITS
     shri
    0.07
     Lee
    0.06
     लगभग
    0.06
     relacion
    0.06
    ILLED
    0.06
    俺は
    0.06
    _EM
    0.06
    ainty
    0.06
     �
    0.06
    simd
    0.06
    Act Density 0.033%

    No Known Activations