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

    Neuronpedia

    INDEX
    Explanations

    Our

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plat
    -0.07
     detects
    -0.07
     plugs
    -0.07
    _usage
    -0.07
     chu
    -0.06
    telefono
    -0.06
     Dire
    -0.06
     tarif
    -0.06
     PUS
    -0.06
     solves
    -0.06
    POSITIVE LOGITS
    ительность
    0.07
     jeune
    0.07
    getName
    0.07
    umbing
    0.07
     eher
    0.07
    =/
    0.06
     spoilers
    0.06
     ihrem
    0.06
     +#+
    0.06
     ราค
    0.06
    Act Density 0.025%

    No Known Activations