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

    Neuronpedia

    INDEX
    Explanations

    Conversational AI/code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rich
    -0.08
    =utf
    -0.08
    禄
    -0.08
     Zion
    -0.07
    elli
    -0.07
    ék
    -0.07
    ersed
    -0.07
     Liu
    -0.07
     smear
    -0.07
    idders
    -0.07
    POSITIVE LOGITS
     Call
    0.07
    -offset
    0.07
    #$
    0.06
     '
↵
    0.06
     tecrübe
    0.06
    ints
    0.06
     обраща
    0.06
    Dictionary
    0.06
     Def
    0.06
    vb
    0.06
    Act Density 0.011%

    No Known Activations