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

    Neuronpedia

    INDEX
    Explanations

    powers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .PI
    -0.07
    _TI
    -0.07
    	sql
    -0.06
    gota
    -0.06
     Grid
    -0.06
     Adaptive
    -0.06
     stimulation
    -0.06
    _Str
    -0.06
    _RST
    -0.06
     Martins
    -0.06
    POSITIVE LOGITS
    cedures
    0.07
     distracted
    0.07
    otics
    0.07
    (Menu
    0.07
    希望
    0.06
    rung
    0.06
    かの
    0.06
     Benefits
    0.06
    lover
    0.06
    先
    0.06
    Act Density 0.005%

    No Known Activations