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

    Neuronpedia

    INDEX
    Explanations

    gh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    QUEST
    -0.06
    ,F
    -0.06
     destiny
    -0.06
    levels
    -0.06
     TOK
    -0.06
     hard
    -0.06
    BUR
    -0.06
     SUS
    -0.06
     Joan
    -0.06
     Hard
    -0.06
    POSITIVE LOGITS
    ần
    0.07
     ImmutableList
    0.06
    Static
    0.06
    بل
    0.06
    ält
    0.06
     gm
    0.06
     inverse
    0.06
     discriminator
    0.06
     valeurs
    0.06
    .');
↵
    0.06
    Act Density 0.002%

    No Known Activations