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

    Neuronpedia

    INDEX
    Explanations

    Letter clarification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    roducing
    -0.07
    atable
    -0.06
    👫
    -0.06
    Mate
    -0.06
     fam
    -0.06
    Canon
    -0.06
    Injector
    -0.06
    最具
    -0.06
    .equ
    -0.06
    社
    -0.06
    POSITIVE LOGITS
    xA
    0.08
     dysfunctional
    0.07
     Classic
    0.07
    vn
    0.07
     prune
    0.07
    {x
    0.07
    ncpy
    0.07
    nonce
    0.07
    坚持
    0.07
    prt
    0.07
    Act Density 0.079%

    No Known Activations