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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atted
    -0.08
     Juan
    -0.07
     alumni
    -0.07
    _auto
    -0.07
    !!↵↵
    -0.07
    兰州
    -0.07
    急性
    -0.07
     미래
    -0.07
     Mega
    -0.07
    صندوق
    -0.07
    POSITIVE LOGITS
    omit
    0.07
    љ
    0.06
    ละเอ
    0.06
    -supported
    0.06
    ritel
    0.06
    ViewState
    0.06
    opa
    0.06
     cdecl
    0.06
    wal
    0.06
    EI
    0.06
    Act Density 0.050%

    No Known Activations