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

    Neuronpedia

    INDEX
    Explanations

    fines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     early
    -0.28
    COMP
    -0.26
    _partial
    -0.26
    early
    -0.26
    禽
    -0.25
    ób
    -0.25
     Aust
    -0.25
    AttributeName
    -0.24
    DrawerToggle
    -0.24
     comp
    -0.24
    POSITIVE LOGITS
    LLU
    0.27
    mir
    0.26
    esthetic
    0.26
    illin
    0.26
    é¢ij
    0.26
    UnderTest
    0.25
     '&#
    0.25
    elles
    0.25
    abad
    0.24
     cold
    0.24
    Act Density 0.007%

    No Known Activations