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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    享
    -0.07
    ā
    -0.06
     Pars
    -0.06
    цо
    -0.06
    tection
    -0.06
     Capacity
    -0.06
     cw
    -0.06
    .un
    -0.06
    听
    -0.06
    -val
    -0.05
    POSITIVE LOGITS
    Ens
    0.07
    ingu
    0.07
    _SYS
    0.07
     disillusion
    0.07
    чист
    0.07
    Policy
    0.07
     AppState
    0.06
    .SelectCommand
    0.06
    Mail
    0.06
     setBackgroundImage
    0.06
    Act Density 0.190%

    No Known Activations