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

    Neuronpedia

    INDEX
    Explanations

    constant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hyp
    -0.07
    Party
    -0.07
     یعنی
    -0.06
    aims
    -0.06
     freely
    -0.06
     dal
    -0.06
     Microwave
    -0.06
    кість
    -0.06
     đảo
    -0.06
    called
    -0.06
    POSITIVE LOGITS
     *>(
    0.07
     Temmuz
    0.06
    asyon
    0.06
     %
    0.06
    }`,
    0.06
     Alphabet
    0.06
    VERTISE
    0.06
    estone
    0.06
    �
    0.06
    지만
    0.06
    Act Density 0.028%

    No Known Activations