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

    Neuronpedia

    INDEX
    Explanations

    company growth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    STANCE
    -0.07
     Couple
    -0.07
     Trojan
    -0.07
     бактер
    -0.06
    ▏▏
    -0.06
     Fel
    -0.06
     bathtub
    -0.06
     glamour
    -0.06
     
    -0.06
    .worker
    -0.06
    POSITIVE LOGITS
    epsilon
    0.07
    NÍ
    0.06
    є
    0.06
     laughs
    0.06
    花
    0.06
    /********************************************************
    0.06
    LIGHT
    0.06
    ASM
    0.06
     oblivious
    0.06
     inputs
    0.06
    Act Density 0.022%

    No Known Activations