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

    Neuronpedia

    INDEX
    Explanations

    numerical ratios and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tuna
    -0.07
    	page
    -0.06
    ETA
    -0.06
     Tw
    -0.06
     labels
    -0.06
    ért
    -0.06
    bgcolor
    -0.06
    _outline
    -0.06
    leshoot
    -0.06
    	output
    -0.06
    POSITIVE LOGITS
    buff
    0.07
    _VOICE
    0.07
    ційні
    0.06
    کاران
    0.06
    -gr
    0.06
    Authentication
    0.06
    _connector
    0.06
    _ANS
    0.06
    _Cmd
    0.06
    Associate
    0.06
    Act Density 0.057%

    No Known Activations