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
    _network
    -0.07
     latino
    -0.07
    _mysql
    -0.07
    _money
    -0.07
     brethren
    -0.06
     Lexer
    -0.06
     svém
    -0.06
     Christoph
    -0.06
     Destroy
    -0.06
    constraints
    -0.06
    POSITIVE LOGITS
     Revenge
    0.06
    ths
    0.06
    LastError
    0.06
    Repeat
    0.06
     delivered
    0.06
    787
    0.06
    Pres
    0.06
    タ
    0.06
     girl
    0.06
    ép
    0.06
    Act Density 0.001%

    No Known Activations