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

    Neuronpedia

    INDEX
    Explanations

    told

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SYSTEM
    -0.08
    ++↵↵
    -0.07
     running
    -0.07
     Forgotten
    -0.07
     Haziran
    -0.07
    ALA
    -0.07
     seminar
    -0.06
    maker
    -0.06
    INSTALL
    -0.06
    _accept
    -0.06
    POSITIVE LOGITS
    olon
    0.07
    antt
    0.06
     Kov
    0.06
    lew
    0.06
    .of
    0.06
     působ
    0.06
     Francesco
    0.06
    geist
    0.05
    üst
    0.05
     acompanh
    0.05
    Act Density 0.019%

    No Known Activations