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

    Neuronpedia

    INDEX
    Explanations

    diverse snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.71
    aarrggbb
    -0.57
    endish
    -0.52
    jší
    -0.47
     ägg
    -0.47
    WhereInput
    -0.47
     صوتيه
    -0.46
    dibles
    -0.46
     wireType
    -0.45
     Signalez
    -0.45
    POSITIVE LOGITS
    RequestContext
    0.52
     esterni
    0.50
     Pud
    0.49
     otomatig
    0.49
    DebuggerStep
    0.49
     ayudarte
    0.49
    ومات
    0.48
    נטרנט
    0.48
    consulté
    0.47
    ICR
    0.46
    Act Density 0.000%

    No Known Activations