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

    Neuronpedia

    INDEX
    Explanations

    warning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chests
    -0.07
     opposing
    -0.06
    딩
    -0.06
     meanings
    -0.06
     bins
    -0.06
     routing
    -0.06
    .accounts
    -0.06
     vacancies
    -0.06
    iblings
    -0.06
    -develop
    -0.06
    POSITIVE LOGITS
     κ
    0.07
     iam
    0.06
    shiv
    0.06
    (pc
    0.06
    wig
    0.06
    _PANEL
    0.06
    Kill
    0.06
    (frame
    0.06
    cpy
    0.06
    	es
    0.06
    Act Density 0.004%

    No Known Activations