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

    Neuronpedia

    INDEX
    Explanations

    permissions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rocket
    -0.07
    (dataset
    -0.07
     Assessment
    -0.07
    ĐT
    -0.06
    blr
    -0.06
    (Code
    -0.06
    .df
    -0.06
     Institute
    -0.06
    /archive
    -0.06
     FALL
    -0.06
    POSITIVE LOGITS
     permissions
    0.12
    Permission
    0.10
     permission
    0.09
    permissions
    0.09
    _PERMISSION
    0.09
    _permissions
    0.09
    Permissions
    0.08
    .permission
    0.08
    _permission
    0.08
    러운
    0.08
    Act Density 0.010%

    No Known Activations