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

    Neuronpedia

    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Agree
    -0.07
    GeV
    -0.06
    جات
    -0.06
    .TextImageRelation
    -0.06
    ポ
    -0.06
     Ваш
    -0.06
     پژوهش
    -0.06
     GW
    -0.06
    incible
    -0.06
     cud
    -0.06
    POSITIVE LOGITS
     UM
    0.07
    'I
    0.06
    :^(
    0.06
     vulnerability
    0.06
    oom
    0.06
    	dev
    0.06
     Argentina
    0.06
    ILL
    0.06
     должна
    0.06
    %C
    0.06
    Act Density 0.015%

    No Known Activations