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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,private
    -0.08
     herbs
    -0.06
    nst
    -0.06
    Safe
    -0.06
    Structure
    -0.06
     instal
    -0.05
     '?
    -0.05
    eva
    -0.05
    ns
    -0.05
    (?
    -0.05
    POSITIVE LOGITS
     کرد
    0.07
    .walk
    0.07
     BU
    0.06
    .rcParams
    0.06
    (filters
    0.06
    apus
    0.06
    _MUTEX
    0.06
     каж
    0.06
    ارت
    0.06
     relentlessly
    0.06
    Act Density 0.008%

    No Known Activations