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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.63
     pinulongan
    -0.57
    -
    -0.53
    IsContent
    -0.51
     na
    -0.50
    that
    -0.47
     that
    -0.46
     they
    -0.46
    they
    -0.46
    ⓧ
    -0.46
    POSITIVE LOGITS
     uſe
    0.96
     myſelf
    0.96
     ་་
    0.94
     ſind
    0.84
     alſo
    0.81
    endphp
    0.81
     FetchType
    0.79
     itſelf
    0.79
    ñores
    0.78
     podjela
    0.75
    Act Density 0.368%

    No Known Activations