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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    awtextra
    -0.60
    InjectAttribute
    -0.60
     ©️
    -0.58
     CommonModule
    -0.55
     attacking
    -0.51
     alleging
    -0.51
     rosse
    -0.50
    strerror
    -0.50
     întâ
    -0.50
     parche
    -0.50
    POSITIVE LOGITS
     survival
    0.63
    survival
    0.55
     Survival
    0.54
     existence
    0.54
     exist
    0.52
     liberation
    0.52
     survie
    0.52
     esist
    0.51
    Survival
    0.50
     snippetHide
    0.50
    Act Density 0.016%

    No Known Activations