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

    Neuronpedia

    INDEX
    Explanations

    Categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Charlie
    -0.06
     schema
    -0.06
    entral
    -0.06
     �
    -0.06
    δά
    -0.06
    244
    -0.06
    ctrl
    -0.06
     unos
    -0.06
    ानव
    -0.06
    Coverage
    -0.06
    POSITIVE LOGITS
     STATES
    0.07
    処
    0.07
     сказал
    0.07
    peek
    0.07
    _PLL
    0.07
     herhangi
    0.07
    lıyor
    0.06
    ています
    0.06
     행동
    0.06
     paste
    0.06
    Act Density 0.018%

    No Known Activations