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

    Neuronpedia

    INDEX
    Explanations

    payment terms negotiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     discer
    0.39
    ゲスト
    0.37
    fluid
    0.37
    apsed
    0.37
    vascular
    0.37
    auce
    0.37
    cha
    0.35
     pop
    0.35
    pop
    0.35
    ふる
    0.34
    POSITIVE LOGITS
     Bloomberg
    0.43
     nä
    0.41
    掠
    0.41
     apapun
    0.41
     Age
    0.40
     Password
    0.39
     čega
    0.39
     cazul
    0.38
    ancang
    0.38
    denes
    0.38
    Act Density 0.000%

    No Known Activations