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

    Neuronpedia

    INDEX
    Explanations

    none of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     totaling
    -0.07
    Down
    -0.07
    .Args
    -0.07
     Muslims
    -0.06
    ีข
    -0.06
    memory
    -0.06
     cavern
    -0.06
     localize
    -0.06
    Apollo
    -0.06
     lãi
    -0.06
    POSITIVE LOGITS
     helium
    0.07
    .ReactNode
    0.06
    �
    0.06
    сия
    0.06
     Sommer
    0.06
    ittings
    0.06
     compulsory
    0.06
    celain
    0.06
    (Frame
    0.06
     mùa
    0.06
    Act Density 0.011%

    No Known Activations