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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ima
    -0.07
    ({...
    -0.06
     takový
    -0.06
    .OneToOne
    -0.06
     Iss
    -0.06
    nge
    -0.06
    _DU
    -0.06
     same
    -0.06
    .refs
    -0.06
     Alloy
    -0.06
    POSITIVE LOGITS
    priv
    0.07
    greens
    0.07
    _wire
    0.07
     medals
    0.07
     salvage
    0.07
     detriment
    0.07
    -wow
    0.06
     получ
    0.06
     избав
    0.06
     Asc
    0.06
    Act Density 0.076%

    No Known Activations