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

    Neuronpedia

    INDEX
    Explanations

    Clown

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     valida
    -0.07
     '<%=
    -0.07
    вичай
    -0.06
    _preference
    -0.06
     název
    -0.06
     dzi
    -0.06
     dolay
    -0.06
    ４
    -0.06
     karş
    -0.06
    転
    -0.06
    POSITIVE LOGITS
     mate
    0.07
     misinformation
    0.06
     Psych
    0.06
    IPC
    0.06
     FH
    0.06
     inclusive
    0.06
    희
    0.06
    �
    0.06
     ↵ ↵
    0.06
     празд
    0.06
    Act Density 0.001%

    No Known Activations