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

    Neuronpedia

    INDEX
    Explanations

    Dash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -pt
    -0.29
    ipse
    -0.26
     Defaults
    -0.25
     Thumb
    -0.25
     Priv
    -0.25
    PageIndex
    -0.25
    endency
    -0.24
     Permit
    -0.24
    pw
    -0.24
    éģı
    -0.24
    POSITIVE LOGITS
    ropolitan
    0.28
     *(*
    0.27
    fest
    0.26
    år
    0.24
    avit
    0.24
     booster
    0.24
    ument
    0.23
    /+
    0.23
    åĸı
    0.23
    侯
    0.23
    Act Density 0.020%

    No Known Activations