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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Portale
    -0.86
    enumi
    -0.71
    enumii
    -0.71
    genstein
    -0.69
    ResumeLayout
    -0.59
    utable
    -0.57
     convaincre
    -0.56
    yourself
    -0.56
     Changing
    -0.54
    plevel
    -0.53
    POSITIVE LOGITS
     dint
    0.61
     way
    0.54
     means
    0.50
     inscription
    0.46
     she
    0.45
     recycling
    0.45
    optString
    0.44
    endregion
    0.43
     Wiktionnaire
    0.43
     spoke
    0.42
    Act Density 0.001%

    No Known Activations