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

    Neuronpedia

    INDEX
    Explanations

    trajectory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suck
    -0.06
     colder
    -0.06
    143
    -0.06
     honestly
    -0.06
     sharp
    -0.06
    нили
    -0.06
    이라고
    -0.06
     Pedro
    -0.06
     CX
    -0.06
    AMES
    -0.06
    POSITIVE LOGITS
     우
    0.07
    ?";↵
    0.07
     costume
    0.06
    */
↵
    0.06
     Corps
    0.06
     떠
    0.06
     Kut
    0.06
    П
    0.06
     readdir
    0.06
    Per
    0.06
    Act Density 0.000%

    No Known Activations