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

    Neuronpedia

    INDEX
    Explanations

    Story generation instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    риг
    -0.08
     विश्वास
    -0.08
     અગ
    -0.08
     trustworthy
    -0.08
     trust
    -0.07
    ರೆ
    -0.07
     الخدمة
    -0.07
     dependable
    -0.07
    SIDE
    -0.07
    ><?
    -0.07
    POSITIVE LOGITS
     eventual
    0.10
     eventually
    0.09
     Eventually
    0.09
    later
    0.08
    taf
    0.08
    Eventually
    0.08
     이렇게
    0.08
     Economy
    0.07
    MOD
    0.07
     Developed
    0.07
    Act Density 0.040%

    No Known Activations