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

    Neuronpedia

    INDEX
    Explanations

    Job applications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    riend
    -0.06
     standardized
    -0.06
    sgiving
    -0.06
     skeptic
    -0.06
    view
    -0.06
     tearDown
    -0.06
    Metadata
    -0.06
     leo
    -0.06
    Theta
    -0.06
     expelled
    -0.06
    POSITIVE LOGITS
    _EXCEPTION
    0.07
    
    0.07
     tart
    0.06
    ltr
    0.06
    víc
    0.06
    authorize
    0.06
     Ки
    0.06
    먹
    0.06
    ramer
    0.06
    舰
    0.06
    Act Density 0.015%

    No Known Activations