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

    Neuronpedia

    INDEX
    Explanations

    Company operations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rhs
    -0.07
     Boxes
    -0.06
    銀行
    -0.06
    Example
    -0.06
     phrases
    -0.06
    (w
    -0.06
     UIKit
    -0.06
     Spit
    -0.06
     vorhand
    -0.06
    mobx
    -0.06
    POSITIVE LOGITS
    �
    0.07
     Mission
    0.07
    ندق
    0.06
     "*.
    0.06
     RAM
    0.06
    ์ได
    0.06
    psz
    0.06
    的大
    0.06
    -sponsored
    0.06
    IntervalSince
    0.06
    Act Density 0.105%

    No Known Activations