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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anı
    -0.07
     HOME
    -0.07
    dı
    -0.07
    Vault
    -0.07
    -sum
    -0.06
    stricted
    -0.06
    -capital
    -0.06
     Vari
    -0.06
    come
    -0.06
     observes
    -0.06
    POSITIVE LOGITS
    ',↵↵
    0.07
    *-
    0.06
    σει
    0.06
     Forbes
    0.06
     whirl
    0.06
    juries
    0.06
    ’↵
    0.06
    다가
    0.06
    ||↵
    0.06
    '>";↵
    0.06
    Act Density 0.000%

    No Known Activations