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

    Neuronpedia

    INDEX
    Explanations

    valid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    僻
    -0.08
    ref
    -0.08
    =rand
    -0.08
    .setText
    -0.07
     monetary
    -0.07
    的土地
    -0.07
    にお
    -0.07
    항
    -0.07
     TERMS
    -0.07
    tin
    -0.07
    POSITIVE LOGITS
    mış
    0.07
    upa
    0.07
     Müdürl
    0.07
    Stra
    0.07
    ㅒ
    0.06
     bosses
    0.06
     Geme
    0.06
    �
    0.06
     Opera
    0.06
     Juda
    0.06
    Act Density 0.005%

    No Known Activations