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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    constitution
    -0.07
    کان
    -0.07
    nicos
    -0.07
    <State
    -0.07
     attractive
    -0.07
     awakeFromNib
    -0.07
     catalyst
    -0.07
    .readValue
    -0.06
     갈
    -0.06
    ẫn
    -0.06
    POSITIVE LOGITS
    �
    0.06
    робіт
    0.06
    ΣΤ
    0.06
     epoxy
    0.06
     clientele
    0.06
    :int
    0.06
     earliest
    0.06
     đứ
    0.06
    
    0.06
    -ob
    0.06
    Act Density 0.010%

    No Known Activations