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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Dispatcher
    -0.08
     relocation
    -0.07
    _ALLOC
    -0.07
    _SIG
    -0.07
    @(
    -0.07
    STACK
    -0.07
     quán
    -0.07
    AppComponent
    -0.07
     resolves
    -0.07
     SIG
    -0.07
    POSITIVE LOGITS
    (de
    0.06
    (strings
    0.06
    .Diff
    0.06
    今
    0.06
    	const
    0.06
     Erotik
    0.06
    让人
    0.06
     중심
    0.06
    杀了
    0.06
     Berry
    0.06
    Act Density 0.004%

    No Known Activations