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

    Neuronpedia

    INDEX
    Explanations

    strings of numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     helium
    -0.07
    Water
    -0.07
     миним
    -0.07
     Β
    -0.07
    �
    -0.07
     projektu
    -0.06
    सल
    -0.06
    آ
    -0.06
     нал
    -0.06
    elm
    -0.06
    POSITIVE LOGITS
     pause
    0.06
    isks
    0.06
     Morrow
    0.06
    ickým
    0.06
     Strauss
    0.06
    \Entity
    0.06
    :test
    0.06
    Above
    0.06
    .IGNORE
    0.06
    ≠
    0.06
    Act Density 0.108%

    No Known Activations