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

    Neuronpedia

    INDEX
    Explanations

    Signatures or approval

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cipher
    -0.08
    Hasher
    -0.08
    tons
    -0.07
     속
    -0.07
    세
    -0.07
    。でも
    -0.07
    勢
    -0.07
    281
    -0.07
     Fortunately
    -0.07
    ther
    -0.07
    POSITIVE LOGITS
    确认
    0.11
    认可
    0.11
     സ്ഥിരീകര
    0.10
    approve
    0.10
     approve
    0.10
     approving
    0.10
     approval
    0.10
     aprobar
    0.10
    inisek
    0.09
     verify
    0.09
    Act Density 0.014%

    No Known Activations