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

    Neuronpedia

    INDEX
    Explanations

    league

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    שפע
    -0.08
    Atlantic
    -0.07
     curso
    -0.07
     SSA
    -0.07
    Stamp
    -0.07
    inspace
    -0.07
    ,end
    -0.07
     CSR
    -0.07
     '_
    -0.07
     centres
    -0.07
    POSITIVE LOGITS
     móg
    0.07
    .validator
    0.07
    ewhat
    0.06
    带头人
    0.06
     mężczyzn
    0.06
    <Token
    0.06
     detainees
    0.06
    .tiles
    0.06
    otte
    0.06
    /embed
    0.06
    Act Density 0.031%

    No Known Activations