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

    Neuronpedia

    INDEX
    Explanations

    each other's company

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ees
    -0.07
     верх
    -0.06
     IDS
    -0.06
     누
    -0.06
     Genome
    -0.06
    mutations
    -0.06
     towers
    -0.06
     believer
    -0.06
    ôi
    -0.06
     �
    -0.05
    POSITIVE LOGITS
     Assist
    0.07
    цен
    0.07
    _press
    0.06
    ран
    0.06
     ejercicio
    0.06
    Fal
    0.06
    اط
    0.06
     arreglo
    0.06
    ersh
    0.06
    cock
    0.06
    Act Density 0.005%

    No Known Activations