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

    Neuronpedia

    INDEX
    Explanations

    sometimes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hollywood
    -0.07
    BILL
    -0.06
     EVE
    -0.06
    -running
    -0.06
     česk
    -0.06
     Hammer
    -0.06
     raided
    -0.06
    Bright
    -0.06
     jealous
    -0.06
    MW
    -0.06
    POSITIVE LOGITS
    .AddInParameter
    0.07
    _Success
    0.07
    σουν
    0.06
    HttpPost
    0.06
    	Init
    0.06
    ≡
    0.06
     closeButton
    0.06
    ，”
    0.06
    妇
    0.06
     ｲ
    0.06
    Act Density 0.021%

    No Known Activations