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

    Neuronpedia

    INDEX
    Explanations

    live

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remedies
    -0.07
     Collapse
    -0.07
     evasion
    -0.06
     Furniture
    -0.06
     exile
    -0.06
    frame
    -0.06
    Marca
    -0.06
     Motion
    -0.06
     Area
    -0.06
    ohan
    -0.06
    POSITIVE LOGITS
    _ra
    0.06
    [@
    0.06
     �
    0.06
    racuse
    0.06
    rad
    0.06
    phyl
    0.06
    ΗΤ
    0.06
    baby
    0.06
     cudd
    0.06
    argument
    0.05
    Act Density 0.007%

    No Known Activations