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

    Neuronpedia

    INDEX
    Explanations

    Make

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    땸
    -0.07
     seq
    -0.07
    general
    -0.07
    滋
    -0.07
    oration
    -0.06
    .Bl
    -0.06
    ㅓ
    -0.06
     baths
    -0.06
    od
    -0.06
    ㌘
    -0.06
    POSITIVE LOGITS
     Bo
    0.07
     Drop
    0.07
    ijken
    0.07
     redesigned
    0.07
    private
    0.07
    ABB
    0.06
    IFICATION
    0.06
    Strike
    0.06
     residential
    0.06
     производ
    0.06
    Act Density 0.001%

    No Known Activations