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

    Neuronpedia

    INDEX
    Explanations

    code related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     automation
    -0.07
     tongue
    -0.07
     Automation
    -0.07
    (rawValue
    -0.06
    ософ
    -0.06
    -Pack
    -0.06
     einz
    -0.06
    Verification
    -0.06
     termination
    -0.06
    ざ
    -0.06
    POSITIVE LOGITS
     Ки
    0.07
     Fedora
    0.06
     closest
    0.06
     أد
    0.06
    ?action
    0.06
    �
    0.06
     Ud
    0.06
     obě
    0.06
    ');"
    0.06
    ائيل
    0.06
    Act Density 0.029%

    No Known Activations