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

    Neuronpedia

    INDEX
    Explanations

    non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slaughter
    -0.07
     cover
    -0.06
     поп
    -0.06
     bychom
    -0.06
     refining
    -0.06
     pitched
    -0.06
    SearchParams
    -0.06
    Br
    -0.06
     surrounding
    -0.06
    ^n
    -0.05
    POSITIVE LOGITS
    idential
    0.07
    pled
    0.07
    ใกล
    0.07
    áři
    0.06
     Accessibility
    0.06
    洁
    0.06
    .inputs
    0.06
    :value
    0.06
    oggles
    0.06
     Impact
    0.06
    Act Density 0.021%

    No Known Activations