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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (parsed
    -0.07
    imony
    -0.07
     appear
    -0.06
    quartered
    -0.06
    ISTORY
    -0.06
    putc
    -0.06
     muttered
    -0.06
     pare
    -0.06
    𬣞
    -0.06
     Respond
    -0.06
    POSITIVE LOGITS
    cci
    0.08
    builder
    0.07
     Alejandro
    0.07
    锵
    0.07
    Sex
    0.07
    든지
    0.07
    aggio
    0.07
     olduğunu
    0.06
    .Unsupported
    0.06
    нный
    0.06
    Act Density 0.063%

    No Known Activations