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

    Neuronpedia

    INDEX
    Explanations

    forced entry / breaking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     സ
    -0.09
     beneficiaries
    -0.09
     എണ്ണം
    -0.09
     ഓ
    -0.08
     dưỡng
    -0.08
     recipients
    -0.08
     മഹ
    -0.08
     राशि
    -0.08
     sammeln
    -0.08
     സർക്കാർ
    -0.08
    POSITIVE LOGITS
    破解
    0.13
     circumvent
    0.11
     overcoming
    0.11
     penetrating
    0.10
     assault
    0.10
     hacking
    0.10
     explosives
    0.09
    -assisted
    0.09
     overcame
    0.09
     barrier
    0.09
    Act Density 0.046%

    No Known Activations