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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gale
    -0.07
    �
    -0.06
    _CONSOLE
    -0.06
     lapse
    -0.06
    �
    -0.06
     LLP
    -0.06
    enor
    -0.06
    _hostname
    -0.06
    _APPRO
    -0.06
    coming
    -0.06
    POSITIVE LOGITS
    =my
    0.07
    ملة
    0.07
    Thin
    0.06
     UserService
    0.06
     briefed
    0.06
     Problems
    0.06
     problem
    0.06
     compared
    0.06
    reachable
    0.06
    ерами
    0.06
    Act Density 0.003%

    No Known Activations