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

    Neuronpedia

    INDEX
    Explanations

    field goal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quis
    -0.08
    Chair
    -0.06
     Lars
    -0.06
    Austin
    -0.06
    ultipart
    -0.06
    џЭ
    -0.06
    eping
    -0.06
    าต
    -0.06
    (rec
    -0.06
    mployee
    -0.06
    POSITIVE LOGITS
     hypothetical
    0.07
     envelop
    0.07
    .cert
    0.07
    	entry
    0.07
    buah
    0.06
    .Pattern
    0.06
     profits
    0.06
    _soup
    0.06
    .charAt
    0.06
    .second
    0.06
    Act Density 0.002%

    No Known Activations