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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (policy
    -0.06
     precarious
    -0.06
    compressed
    -0.06
    .closed
    -0.06
    클
    -0.06
    Interesting
    -0.06
    벽
    -0.06
    IconModule
    -0.06
     entwick
    -0.06
     �
    -0.05
    POSITIVE LOGITS
    ITER
    0.07
    olla
    0.07
    !<
    0.07
    idi
    0.07
    /demo
    0.07
    cluding
    0.06
    ladesh
    0.06
     biod
    0.06
     ngọt
    0.06
     realloc
    0.06
    Act Density 0.000%

    No Known Activations