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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gala
    -0.06
     спря
    -0.06
    Zend
    -0.06
     vs
    -0.06
    EXAMPLE
    -0.06
     Zend
    -0.06
     hence
    -0.06
    ");}↵
    -0.05
    -0.05
     chess
    -0.05
    POSITIVE LOGITS
    attern
    0.07
    ativa
    0.07
     kork
    0.07
    モン
    0.07
    ział
    0.06
    .onViewCreated
    0.06
    _FA
    0.06
     COD
    0.06
    ações
    0.06
    ação
    0.06
    Act Density 0.008%

    No Known Activations