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

    Neuronpedia

    INDEX
    Explanations

    households

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rew
    -0.07
     TAM
    -0.06
     Transformer
    -0.06
     stk
    -0.06
     Evo
    -0.06
    Xã
    -0.06
    *",
    -0.06
     cả
    -0.06
    Receive
    -0.06
    interpret
    -0.06
    POSITIVE LOGITS
    !important
    0.07
     دهید
    0.07
     azal
    0.06
    -weight
    0.06
     Difficulty
    0.06
    .points
    0.06
     timeStamp
    0.06
    Doctrine
    0.06
    >↵↵
    0.06
    icycle
    0.06
    Act Density 0.000%

    No Known Activations