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

    Neuronpedia

    INDEX
    Explanations

    remove

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alone
    -0.06
    _available
    -0.06
    authenticate
    -0.06
     Аф
    -0.06
    ijn
    -0.06
     homeowners
    -0.06
    Manifest
    -0.06
    Until
    -0.06
    -game
    -0.06
    Chron
    -0.06
    POSITIVE LOGITS
     Losing
    0.07
     περ
    0.06
     тор
    0.06
    expanded
    0.06
     推
    0.06
     Cr
    0.06
    .Chrome
    0.06
    End
    0.06
     Entities
    0.06
    Soft
    0.06
    Act Density 0.021%

    No Known Activations