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

    Neuronpedia

    INDEX
    Explanations

    you followed by need or modal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     insistence
    0.47
     demands
    0.39
     worthy
    0.39
    conductivity
    0.38
    และการ
    0.38
     tendencies
    0.38
    agreement
    0.38
     সকল
    0.37
    ishments
    0.37
    不妨
    0.37
    POSITIVE LOGITS
     essentially
    0.73
     basically
    0.59
    Essentially
    0.54
     Essentially
    0.52
     manipulate
    0.51
    essentially
    0.49
     necesitar
    0.49
     need
    0.49
     typically
    0.49
     benötigen
    0.48
    Act Density 0.012%

    No Known Activations