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

    Neuronpedia

    INDEX
    Explanations

    Formal/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iterals
    -0.07
    -ref
    -0.06
     enerji
    -0.06
    buscar
    -0.06
    sville
    -0.06
    ercise
    -0.06
     monde
    -0.06
    者的
    -0.06
    .ingredients
    -0.06
     CHUNK
    -0.06
    POSITIVE LOGITS
     compet
    0.07
    (u
    0.07
     건
    0.07
     UR
    0.07
    TOR
    0.06
     CU
    0.06
    EXTERN
    0.06
     NF
    0.06
     金
    0.06
     professional
    0.06
    Act Density 0.296%

    No Known Activations