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

    Neuronpedia

    INDEX
    Explanations

    ed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    heck
    -0.08
     jogo
    -0.08
    主帅
    -0.07
     Timeline
    -0.07
    umbnail
    -0.07
    נושא
    -0.07
    )sender
    -0.07
     Hind
    -0.07
     nullable
    -0.07
     confess
    -0.07
    POSITIVE LOGITS
    גת
    0.07
     little
    0.07
     paternal
    0.07
    เภ
    0.07
    patients
    0.06
    搛
    0.06
    解放军
    0.06
    tha
    0.06
    膨
    0.06
     inse
    0.06
    Act Density 0.001%

    No Known Activations