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

    Neuronpedia

    INDEX
    Explanations

    immediate danger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Det
    0.41
     Gri
    0.39
     Devi
    0.37
     Fib
    0.36
     det
    0.36
    ۔
    0.36
     Poss
    0.36
     Hak
    0.35
     sempre
    0.35
     Reasons
    0.35
    POSITIVE LOGITS
     mActivity
    0.46
    年モデル
    0.45
     allait
    0.44
    TARGETTING
    0.44
     fallait
    0.43
     inwoners
    0.43
     añadido
    0.42
    HttpFoundation
    0.42
     sweeteners
    0.41
     invariants
    0.40
    Act Density 0.001%

    No Known Activations