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

    Neuronpedia

    INDEX
    Explanations

    version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nerRadius
    -0.07
    fuck
    -0.07
    ksam
    -0.06
    eşit
    -0.06
    heel
    -0.06
     dây
    -0.06
     betrayal
    -0.06
    hard
    -0.06
    _t
    -0.06
    _ste
    -0.06
    POSITIVE LOGITS
    ──
    0.07
    OnInit
    0.07
    NSMutableArray
    0.07
    =options
    0.07
    (term
    0.06
     continual
    0.06
     proportional
    0.06
    DropDown
    0.06
    	namespace
    0.06
    '])
↵
    0.06
    Act Density 0.000%

    No Known Activations