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

    Neuronpedia

    INDEX
    Explanations

    talks/negotiations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Space
    -0.07
     tract
    -0.07
    (ne
    -0.07
    fh
    -0.06
     most
    -0.06
     Suicide
    -0.06
     Benson
    -0.06
    Explicit
    -0.06
     örgüt
    -0.06
     film
    -0.06
    POSITIVE LOGITS
     JsonRequestBehavior
    0.06
     misguided
    0.06
    .obtain
    0.06
     Dear
    0.06
    _Application
    0.06
    िज
    0.06
    .LogWarning
    0.06
    contra
    0.06
    .v
    0.06
    @Controller
    0.06
    Act Density 0.000%

    No Known Activations