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

    Neuronpedia

    INDEX
    Explanations

    Decisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Joe
    -0.07
    听话
    -0.07
     представля
    -0.07
     retina
    -0.07
     propulsion
    -0.06
    ünk
    -0.06
     silk
    -0.06
     makes
    -0.06
    Sparse
    -0.06
    -0.06
    POSITIVE LOGITS
    loggedin
    0.08
     Rencontres
    0.07
    שמת
    0.07
    光影
    0.07
    uxt
    0.07
    erview
    0.07
    mdir
    0.07
    _owner
    0.06
     nonzero
    0.06
    PROCESS
    0.06
    Act Density 0.053%

    No Known Activations