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

    Neuronpedia

    INDEX
    Explanations

    showed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ś
    -0.07
    _started
    -0.06
    urent
    -0.06
    _the
    -0.06
    utr
    -0.06
    .var
    -0.06
     the
    -0.06
    _reset
    -0.06
     unnamed
    -0.06
    Agent
    -0.06
    POSITIVE LOGITS
     veterin
    0.06
    	gr
    0.06
    “Well
    0.06
     Diese
    0.06
    rem
    0.06
     bzw
    0.05
     Class
    0.05
    "Well
    0.05
     electrom
    0.05
     sharedPreferences
    0.05
    Act Density 0.040%

    No Known Activations