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

    Neuronpedia

    INDEX
    Explanations

    Java or Go code

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     $[
    -1.23
     [
    -1.23
    =[
    -1.20
    }=[
    -1.06
    :[
    -1.05
    ([
    -1.05
     [-
    -1.03
    [
    -1.01
     =[
    -1.00
    }[
    -0.99
    POSITIVE LOGITS
    ējās
    0.48
    brido
    0.48
    жешь
    0.47
    cardia
    0.46
     AssemblyProduct
    0.46
    isem
    0.45
     ModelExpression
    0.43
    íticas
    0.43
     poil
    0.42
     gefe
    0.42
    Act Density 0.646%

    No Known Activations