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

    Neuronpedia

    INDEX
    Explanations

    new product/company description

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ether
    -0.07
     форме
    -0.06
    ETHER
    -0.06
    gravity
    -0.06
    -----------
    -0.06
    ержав
    -0.06
    .NotNull
    -0.06
     cháy
    -0.06
    urret
    -0.06
    avourite
    -0.05
    POSITIVE LOGITS
     talks
    0.07
    건
    0.07
    400
    0.07
    ΩΣ
    0.07
    =%
    0.07
     folded
    0.07
     опера
    0.07
     di
    0.07
     talk
    0.07
    няття
    0.07
    Act Density 0.012%

    No Known Activations