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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ting
    -0.07
     tide
    -0.07
     dédi
    -0.07
     drastic
    -0.07
    (Content
    -0.07
     reserv
    -0.07
    (Str
    -0.07
     ziehen
    -0.07
    ("{}
    -0.07
     downg
    -0.07
    POSITIVE LOGITS
    Goal
    0.08
    īj
    0.08
     analyt
    0.07
     Здесь
    0.07
    Want
    0.07
     ANAL
    0.07
    smouth
    0.07
    Aim
    0.07
     parentheses
    0.07
     aim
    0.07
    Act Density 0.135%

    No Known Activations