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

    Neuronpedia

    INDEX
    Explanations

    Technical/scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     summit
    -0.06
     арх
    -0.06
     Аф
    -0.06
    ixin
    -0.06
     سم
    -0.06
     boh
    -0.06
    บบ
    -0.06
    _sum
    -0.06
    WH
    -0.06
    andi
    -0.06
    POSITIVE LOGITS
     JsonRequestBehavior
    0.08
     injecting
    0.06
    munition
    0.06
    "user
    0.06
    _PROM
    0.06
     vow
    0.06
     Orb
    0.06
     bolster
    0.06
     огля
    0.06
     fileprivate
    0.06
    Act Density 0.029%

    No Known Activations