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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.57
    principalTable
    -0.51
     feeding
    -0.50
    SourceChecksum
    -0.49
    afficheront
    -0.49
    DeleteBehavior
    -0.49
     allAfrica
    -0.49
    脚注の使い方
    -0.47
    gentes
    -0.47
     Fourth
    -0.47
    POSITIVE LOGITS
     have
    0.60
     enjoyed
    0.56
    enumi
    0.56
     read
    0.54
     understand
    0.53
    Aholisi
    0.52
     received
    0.51
     spent
    0.51
     grew
    0.51
     attended
    0.50
    Act Density 0.058%

    No Known Activations