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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surrogate
    -0.06
    _mass
    -0.06
     Кал
    -0.06
    ////////////////////////////////
    -0.05
     appealed
    -0.05
    });↵↵↵↵
    -0.05
     Ir
    -0.05
     withheld
    -0.05
     túi
    -0.05
     dialogue
    -0.05
    POSITIVE LOGITS
    _handles
    0.08
     использовани
    0.07
    oston
    0.07
    .getResources
    0.07
     sincer
    0.06
    .sum
    0.06
    十四
    0.06
    .property
    0.06
    _In
    0.06
    ://
    0.06
    Act Density 0.010%

    No Known Activations