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

    Neuronpedia

    INDEX
    Explanations

    skills and qualifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wat
    -0.07
     下
    -0.06
     перемен
    -0.06
    	auto
    -0.06
    ;\↵
    -0.06
    _ctl
    -0.06
    	h
    -0.05
     اف
    -0.05
    _separator
    -0.05
     я
    -0.05
    POSITIVE LOGITS
    ollect
    0.07
    loss
    0.07
    manı
    0.07
     animated
    0.06
    entially
    0.06
    ления
    0.06
    fidf
    0.06
    anoi
    0.06
    ardy
    0.06
    eters
    0.06
    Act Density 0.098%

    No Known Activations