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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Є
    -0.07
    -carousel
    -0.07
    Expl
    -0.07
     ['./
    -0.07
     Gear
    -0.06
     trata
    -0.06
    grunt
    -0.06
     explicit
    -0.06
    _AMD
    -0.06
    .display
    -0.06
    POSITIVE LOGITS
    	keys
    0.06
     ammonia
    0.06
    DONE
    0.06
     puerto
    0.06
    �m
    0.06
     CASCADE
    0.06
    vak
    0.06
     setType
    0.06
    洞
    0.06
     Schl
    0.06
    Act Density 0.000%

    No Known Activations