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

    Neuronpedia

    INDEX
    Explanations

    engines and motors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >v
    -0.07
    -----------↵↵
    -0.07
    .httpClient
    -0.06
     Python
    -0.06
    ============↵
    -0.06
    _counter
    -0.06
    .thread
    -0.06
    .scal
    -0.06
    ственным
    -0.06
    pwd
    -0.06
    POSITIVE LOGITS
     paranoia
    0.08
    oit
    0.07
     Enhanced
    0.07
     multiline
    0.07
     Frauen
    0.07
     Dai
    0.07
     σας
    0.06
    ارية
    0.06
     sanitized
    0.06
    thetic
    0.06
    Act Density 0.094%

    No Known Activations