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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Moore
    -0.07
    ług
    -0.06
    (found
    -0.06
     governors
    -0.06
    fullname
    -0.06
    sti
    -0.06
     vůči
    -0.06
    fec
    -0.06
    Stick
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    ณฑ
    0.07
     Calc
    0.07
    OOSE
    0.07
     apparatus
    0.06
     addict
    0.06
     calc
    0.06
    shr
    0.06
    JECT
    0.06
     Manafort
    0.06
     insanity
    0.06
    Act Density 0.043%

    No Known Activations