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

    Neuronpedia

    INDEX
    Explanations

    Keyboard shortcuts, navigation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     durchaus
    -0.08
     motives
    -0.08
    וקים
    -0.08
     satria
    -0.08
     permisos
    -0.08
     الأموال
    -0.08
     tamin
    -0.08
    กรรม
    -0.08
     permissions
    -0.08
    Ljava
    -0.08
    POSITIVE LOGITS
     toggle
    0.08
    toggle
    0.08
    (toggle
    0.08
    Nearest
    0.08
     troubleshoot
    0.08
    Toggle
    0.08
     Toggle
    0.08
    _toggle
    0.07
     disbelief
    0.07
    Centered
    0.07
    Act Density 0.009%

    No Known Activations