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

    Neuronpedia

    INDEX
    Explanations

    history and conflict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Safety
    0.47
     Lent
    0.42
     Netanyahu
    0.41
     OSHA
    0.39
     comportamenti
    0.39
    격
    0.38
     Lit
    0.38
     Astrophysics
    0.37
     Nuclear
    0.37
    Safety
    0.37
    POSITIVE LOGITS
     samano
    0.39
    三分
    0.38
    ongs
    0.37
    THREE
    0.37
     draper
    0.37
    ÔNG
    0.37
    antry
    0.37
    अर्स
    0.36
    ᱓
    0.36
     drie
    0.36
    Act Density 0.000%

    No Known Activations