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

    Neuronpedia

    INDEX
    Explanations

    make plans and achieve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     관련
    0.37
     bolder
    0.36
    ಕ್ಷ
    0.35
     pulmonary
    0.34
    holtz
    0.34
     Saad
    0.34
    ueses
    0.34
     તાલુ
    0.33
     Ve
    0.33
     আলম
    0.33
    POSITIVE LOGITS
    Something
    0.55
    something
    0.53
     Something
    0.46
     PLANS
    0.46
    stuff
    0.45
     cosas
    0.42
    計劃
    0.42
    റും
    0.42
    時間
    0.42
     Plans
    0.41
    Act Density 0.006%

    No Known Activations