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

    Neuronpedia

    INDEX
    Explanations

    lens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ogn
    -0.07
     отмет
    -0.07
    نموذ
    -0.07
    Registr
    -0.07
     notion
    -0.07
     impose
    -0.07
    aware
    -0.06
    ombine
    -0.06
     biomass
    -0.06
    ini
    -0.06
    POSITIVE LOGITS
    !!.
    0.07
    roy
    0.07
        ↵↵↵
    0.07
     healed
    0.07
     يؤ
    0.07
    呼和
    0.06
     ")"↵
    0.06
    苏联
    0.06
    noxious
    0.06
     dialogue
    0.06
    Act Density 0.009%

    No Known Activations