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

    Neuronpedia

    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Na
    -0.07
    Jo
    -0.07
     próxima
    -0.07
     translator
    -0.07
    TED
    -0.06
    reno
    -0.06
     ai
    -0.06
    につ
    -0.06
     terminating
    -0.06
     clas
    -0.06
    POSITIVE LOGITS
    .content
    0.07
     환산
    0.06
    /lgpl
    0.06
    lığı
    0.06
    summer
    0.06
    IVERS
    0.06
    -contrib
    0.06
    .ModelForm
    0.06
     assemblies
    0.06
     userName
    0.06
    Act Density 0.006%

    No Known Activations