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

    Neuronpedia

    INDEX
    Explanations

    symbols and characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    summary
    -0.07
    有限
    -0.07
     nye
    -0.07
     liqu
    -0.06
     яких
    -0.06
     reven
    -0.06
     Equal
    -0.06
     soft
    -0.06
    tık
    -0.06
    [id
    -0.06
    POSITIVE LOGITS
     asıl
    0.07
     varsa
    0.07
     })↵↵↵
    0.07
    ापन
    0.06
    <form
    0.06
    _ALLOW
    0.06
    -readable
    0.06
     CString
    0.06
    .code
    0.06
    TARGET
    0.06
    Act Density 0.017%

    No Known Activations