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

    Neuronpedia

    INDEX
    Explanations

    symmetry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bon
    -0.08
     baptized
    -0.07
     Era
    -0.07
     dog
    -0.07
     gently
    -0.06
    Debugger
    -0.06
     reservation
    -0.06
     addressed
    -0.06
     sul
    -0.06
    保
    -0.06
    POSITIVE LOGITS
    ידי
    0.07
     реак
    0.07
     własne
    0.07
    CTYPE
    0.07
    鼷
    0.07
    เมตร
    0.07
    krä
    0.07
     abducted
    0.07
    .Remove
    0.07
    รถย
    0.07
    Act Density 0.001%

    No Known Activations