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

    Neuronpedia

    INDEX
    Explanations

    Punctuation in character counts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nicola
    -0.08
    reta
    -0.08
    anal
    -0.08
     연결
    -0.08
    kert
    -0.07
    GRE
    -0.07
     begrü
    -0.07
    -top
    -0.07
     relish
    -0.07
     Temps
    -0.07
    POSITIVE LOGITS
     worst
    0.10
     counted
    0.08
     rough
    0.08
     markdown
    0.08
     assessment
    0.08
     counting
    0.08
     Feng
    0.08
    衡
    0.08
     calculation
    0.08
     compiling
    0.08
    Act Density 0.015%

    No Known Activations