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

    Neuronpedia

    INDEX
    Explanations

    the Trevor Project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cmb
    0.70
    នុ
    0.70
     kerak
    0.68
    angas
    0.66
     जीरो
    0.66
     सांगित
    0.65
    ての
    0.65
    ilization
    0.64
    STRUCTIONS
    0.64
    emplacement
    0.63
    POSITIVE LOGITS
     Here
    0.74
     queer
    0.71
     Queer
    0.68
     Slowly
    0.67
     LGBT
    0.65
    ása
    0.65
     Pay
    0.64
     Sandy
    0.63
    Here
    0.63
    टीशन
    0.62
    Act Density 0.057%

    No Known Activations