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

    Neuronpedia

    INDEX
    Explanations

    late

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Velocity
    -0.07
    HEY
    -0.06
     Holds
    -0.06
    -automatic
    -0.06
     velký
    -0.06
     تج
    -0.06
     nightclub
    -0.06
     پرس
    -0.06
     identifying
    -0.06
    委
    -0.06
    POSITIVE LOGITS
     slate
    0.25
     Slate
    0.20
     Slater
    0.12
    late
    0.12
    Late
    0.08
    lates
    0.08
     pat
    0.07
     Late
    0.07
    ates
    0.07
     Chatt
    0.07
    Act Density 0.002%

    No Known Activations