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

    Neuronpedia

    INDEX
    Explanations

    scientific papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    series
    -0.07
     Monica
    -0.07
    tester
    -0.07
     sequential
    -0.07
    ester
    -0.07
    ANGLE
    -0.07
    ibe
    -0.06
    oxid
    -0.06
    SET
    -0.06
    Chooser
    -0.06
    POSITIVE LOGITS
     ضمن
    0.07
     쿠
    0.07
     detained
    0.06
     MSR
    0.06
    .constructor
    0.06
     αρ
    0.06
     Αγ
    0.06
    createQuery
    0.06
    )+
    0.06
    Instantiate
    0.06
    Act Density 0.015%

    No Known Activations