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

    Neuronpedia

    INDEX
    Explanations

    code and technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ¿
    -0.07
     approve
    -0.06
     audiences
    -0.06
     �
    -0.06
     kaum
    -0.06
     caves
    -0.06
     hintText
    -0.06
     dựng
    -0.06
    ımı
    -0.06
     WA
    -0.06
    POSITIVE LOGITS
    emm
    0.06
    DET
    0.06
    ritt
    0.06
    .setOutput
    0.06
     activist
    0.06
    *******↵
    0.06
    
    0.06
     punk
    0.06
     Redirect
    0.06
    यर
    0.06
    Act Density 0.077%

    No Known Activations