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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đài
    -0.07
    .CreateDirectory
    -0.07
    .cpu
    -0.07
    ...)↵↵
    -0.07
    Destroyed
    -0.07
     <|
    -0.07
    _Build
    -0.07
    model
    -0.06
     risky
    -0.06
     $"
    -0.06
    POSITIVE LOGITS
     DER
    0.07
     Davidson
    0.07
    -events
    0.07
    ész
    0.07
     freshly
    0.06
    示
    0.06
    ァ
    0.06
    із
    0.06
    .vs
    0.06
     stata
    0.06
    Act Density 0.025%

    No Known Activations