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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     injust
    -0.07
    IDAD
    -0.07
    udiante
    -0.06
     شوند
    -0.06
     deriv
    -0.06
     enumeration
    -0.06
    loven
    -0.06
     Αγ
    -0.06
    >\<^
    -0.06
    +"&
    -0.06
    POSITIVE LOGITS
    iii
    0.07
     النو
    0.07
    nin
    0.07
     Jedi
    0.07
    psc
    0.06
     verbs
    0.06
    olvers
    0.06
    Nic
    0.06
    setDescription
    0.06
    @n
    0.06
    Act Density 0.125%

    No Known Activations