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

    Neuronpedia

    INDEX
    Explanations

    abuse, harassment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ancing
    -0.06
    VIDIA
    -0.06
     proposal
    -0.06
     nesting
    -0.06
     encounter
    -0.06
     proposed
    -0.06
    Trump
    -0.05
    HTTP
    -0.05
    Ja
    -0.05
    еры
    -0.05
    POSITIVE LOGITS
    (QString
    0.07
     gratuit
    0.07
     Appalachian
    0.06
    _void
    0.06
     Vertex
    0.06
     forehead
    0.06
     лич
    0.06
     amounted
    0.06
    ][$
    0.06
    specialchars
    0.06
    Act Density 0.045%

    No Known Activations