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

    Neuronpedia

    INDEX
    Explanations

    Judges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comprom
    -0.07
     similarly
    -0.07
     नय
    -0.06
    ello
    -0.06
     hardened
    -0.06
    .Login
    -0.06
     newArray
    -0.06
     america
    -0.06
    株
    -0.06
     PLAYER
    -0.06
    POSITIVE LOGITS
    ablytyped
    0.07
     Len
    0.06
     tí
    0.06
    oger
    0.06
     etwa
    0.06
    imachinery
    0.06
    vertisement
    0.06
    itmap
    0.06
    ……↵↵
    0.06
     disag
    0.06
    Act Density 0.009%

    No Known Activations