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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hw
    -0.06
    -first
    -0.06
    Ask
    -0.06
    http
    -0.06
     Hil
    -0.06
     bras
    -0.06
    Titan
    -0.06
    orias
    -0.06
    如何
    -0.06
    Had
    -0.06
    POSITIVE LOGITS
    ασ
    0.07
    ypass
    0.07
    ensen
    0.07
    사업
    0.07
    सम
    0.06
    .structure
    0.06
     interpreter
    0.06
    TimeString
    0.06
    .setUser
    0.06
    ffect
    0.06
    Act Density 0.001%

    No Known Activations