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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Constraint
    -0.07
    .shapes
    -0.07
    .Adapter
    -0.07
    .prototype
    -0.06
     гра
    -0.06
     Two
    -0.06
     formulated
    -0.06
     QUEST
    -0.06
    (Pos
    -0.06
     DataFrame
    -0.06
    POSITIVE LOGITS
    علام
    0.06
    彦
    0.06
    jay
    0.06
     Jay
    0.06
    ienne
    0.06
    food
    0.06
    acute
    0.06
    AY
    0.06
    -envelope
    0.06
     этим
    0.06
    Act Density 0.118%

    No Known Activations