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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	action
    -0.07
    Sat
    -0.07
    urr
    -0.07
     supplies
    -0.07
    inars
    -0.07
    Flash
    -0.06
     unload
    -0.06
    柳
    -0.06
    .Current
    -0.06
    _ERR
    -0.06
    POSITIVE LOGITS
     verschiedenen
    0.06
     назва
    0.06
     тисяч
    0.06
     girişim
    0.06
     genuinely
    0.06
    rame
    0.06
     distracting
    0.06
     któ
    0.06
    _MINUS
    0.06
    IsRequired
    0.06
    Act Density 0.003%

    No Known Activations