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

    Neuronpedia

    INDEX
    Explanations

    Code and time mentions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    كل
    -0.08
    รรค
    -0.07
     potrze
    -0.07
    ंभ
    -0.06
    CAR
    -0.06
     컨
    -0.06
     پا
    -0.06
    thy
    -0.06
     TAM
    -0.06
    then
    -0.06
    POSITIVE LOGITS
    地址
    0.07
    Jane
    0.06
     Midnight
    0.06
     praised
    0.06
    Ear
    0.06
     연구
    0.06
    Charles
    0.06
    Lux
    0.06
    _MODE
    0.06
    Universal
    0.06
    Act Density 0.000%

    No Known Activations