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

    Neuronpedia

    INDEX
    Explanations

    dbus paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     promised
    -0.08
     thư
    -0.07
     kvin
    -0.07
    髓
    -0.07
    smith
    -0.07
    monthly
    -0.07
     front
    -0.07
    Mill
    -0.07
    tı
    -0.06
     gute
    -0.06
    POSITIVE LOGITS
    alette
    0.09
    lettes
    0.07
    代言人
    0.07
     Kaepernick
    0.07
    ▹
    0.07
    _DEVICES
    0.07
     upbringing
    0.07
    @example
    0.07
     grabs
    0.07
    _ge
    0.07
    Act Density 0.007%

    No Known Activations