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

    Neuronpedia

    INDEX
    Explanations

    future

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -0.84
     **/
    -0.80
    Obrázky
    -0.77
     itſelf
    -0.75
     iſt
    -0.71
    >\<^
    -0.71
     ſeveral
    -0.70
    .³
    -0.69
    IBOutlet
    -0.68
    */;
    -0.68
    POSITIVE LOGITS
     career
    0.60
    ,
    0.55
    ts
    0.54
    .
    0.51
    :
    0.48
    msg
    0.48
     on
    0.47
    si
    0.46
    use
    0.46
     Career
    0.46
    Act Density 0.093%

    No Known Activations