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

    Neuronpedia

    INDEX
    Explanations

    explosive device, games, firearms, nerve agents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EVA
    0.47
     elephant
    0.46
     eccentric
    0.46
    });
    0.45
     *****
    0.45
    榉
    0.45
     Ayala
    0.44
     店
    0.44
     inspect
    0.44
    σιά
    0.44
    POSITIVE LOGITS
    d
    0.53
    ℓ
    0.53
    U
    0.52
    SCALE
    0.51
    å
    0.48
    Q
    0.47
    o
    0.47
    dj
    0.46
    ன
    0.45
    নার্থ
    0.45
    Act Density 0.000%

    No Known Activations