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

    Neuronpedia

    INDEX
    Explanations

    used to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     goodness
    -0.07
    "name
    -0.07
     rules
    -0.06
    	cnt
    -0.06
     lord
    -0.06
    premium
    -0.06
    job
    -0.06
     dicks
    -0.06
    +</
    -0.06
     divide
    -0.06
    POSITIVE LOGITS
    aza
    0.07
    exao
    0.07
    ода
    0.07
     Vermont
    0.06
    ิโน
    0.06
     كار
    0.06
    ————
    0.06
    usi
    0.06
    바일
    0.06
     لن
    0.06
    Act Density 0.104%

    No Known Activations