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

    Neuronpedia

    INDEX
    Explanations

    Offering or asking for help

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    posted
    -0.08
    beginTransaction
    -0.07
    話し
    -0.07
    umbed
    -0.07
    ultip
    -0.07
    着手
    -0.06
    vang
    -0.06
    (payment
    -0.06
    стро
    -0.06
    -depend
    -0.06
    POSITIVE LOGITS
     COS
    0.07
     Hilton
    0.07
    ⊗
    0.07
    专项行动
    0.07
    (defvar
    0.07
     algorithms
    0.06
     winning
    0.06
     Something
    0.06
    딕
    0.06
    sports
    0.06
    Act Density 0.009%

    No Known Activations