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

    Neuronpedia

    INDEX
    Explanations

    habits, conditions, mathematicians

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    trek
    0.41
    镁
    0.39
    cud
    0.38
     bezieht
    0.38
     .^{
    0.38
     indywidual
    0.37
     ?!
    0.37
    侣
    0.37
     Bezug
    0.37
    魎
    0.36
    POSITIVE LOGITS
     Je
    0.45
     bovine
    0.39
    Z
    0.39
    X
    0.39
    honor
    0.38
     cout
    0.38
     Account
    0.38
     residue
    0.38
     F
    0.38
     X
    0.38
    Act Density 0.000%

    No Known Activations