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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Macro
    -0.07
    _ste
    -0.06
    ّر
    -0.06
     lucr
    -0.06
     RaisePropertyChanged
    -0.06
     Moved
    -0.06
    STIT
    -0.06
    stateProvider
    -0.06
    iers
    -0.06
    cer
    -0.06
    POSITIVE LOGITS
    DELAY
    0.07
    com
    0.06
     routine
    0.06
     pretended
    0.06
     arguing
    0.06
     circuit
    0.06
     lanz
    0.06
    орм
    0.06
    _CRITICAL
    0.06
    WARE
    0.06
    Act Density 0.026%

    No Known Activations