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

    Neuronpedia

    INDEX
    Explanations

    toward

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.89
     AssemblyTitle
    -0.86
     Infórmanos
    -0.80
    TypedDataSet
    -0.80
     betweenstory
    -0.77
     saurait
    -0.73
     CreateTagHelper
    -0.72
     <=",
    -0.71
     noDo
    -0.70
     rayures
    -0.70
    POSITIVE LOGITS
     assuming
    0.65
     ignoring
    0.61
     agreeing
    0.59
     taking
    0.59
     using
    0.59
     over
    0.59
     saying
    0.58
     valuing
    0.57
     including
    0.57
     seeing
    0.56
    Act Density 0.004%

    No Known Activations