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

    Neuronpedia

    INDEX
    Explanations

    showed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Basically
    -0.08
    outputs
    -0.07
     Basically
    -0.07
    ерти
    -0.07
    Cars
    -0.06
    wrap
    -0.06
    !(
    -0.06
     CAPITAL
    -0.06
     requested
    -0.06
    ums
    -0.06
    POSITIVE LOGITS
    spd
    0.07
    .getUrl
    0.06
     mojo
    0.06
     cadena
    0.06
     systemd
    0.06
     kontro
    0.06
    žitě
    0.06
     stran
    0.06
    .localizedDescription
    0.06
     aumento
    0.06
    Act Density 0.145%

    No Known Activations