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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ۲
    -0.07
     hist
    -0.07
     با
    -0.06
     shifting
    -0.06
     homes
    -0.06
     overwhelmed
    -0.06
    //#
    -0.06
     However
    -0.06
     Productions
    -0.06
     fak
    -0.06
    POSITIVE LOGITS
    IONS
    0.07
     Isaac
    0.07
     下午
    0.07
    _length
    0.07
     обыч
    0.07
     Extend
    0.06
    hive
    0.06
    _VM
    0.06
     reassure
    0.06
     rivals
    0.06
    Act Density 0.026%

    No Known Activations