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

    Neuronpedia

    INDEX
    Explanations

    simulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ける
    -0.07
    Α
    -0.06
    <Base
    -0.06
    (Process
    -0.06
     �
    -0.06
    _featured
    -0.06
     Provincial
    -0.06
     orderly
    -0.06
     Kobe
    -0.06
    <Vertex
    -0.06
    POSITIVE LOGITS
    블
    0.07
    .FR
    0.07
    _SR
    0.06
    чив
    0.06
    trfs
    0.06
     disadv
    0.06
    (klass
    0.06
    ранения
    0.06
    /gr
    0.06
     Sheffield
    0.06
    Act Density 0.043%

    No Known Activations