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

    Neuronpedia

    INDEX
    Explanations

    code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Carroll
    -0.07
    531
    -0.07
     dataSet
    -0.07
    _STANDARD
    -0.06
    _assigned
    -0.06
    Particle
    -0.06
    disp
    -0.06
     jméno
    -0.06
    actal
    -0.06
     llama
    -0.06
    POSITIVE LOGITS
     gắn
    0.07
     toen
    0.07
    _exceptions
    0.06
    ุร
    0.06
     html
    0.06
     repell
    0.06
    #.
    0.06
     Getting
    0.06
    지만
    0.06
     Buen
    0.06
    Act Density 0.022%

    No Known Activations