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

    Neuronpedia

    INDEX
    Explanations

    technical or financial terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cristianos
    0.41
    主管部门
    0.40
     atoi
    0.39
     antiseptic
    0.39
    abases
    0.37
     dodat
    0.37
     القرن
    0.37
     oldest
    0.36
     antice
    0.36
    锢
    0.36
    POSITIVE LOGITS
    ELTS
    0.46
    Exposure
    0.44
    Ꮕ
    0.43
    Both
    0.42
    শ্ম
    0.42
    Feel
    0.41
    Press
    0.40
     Feelings
    0.40
    ༥
    0.39
    ༸
    0.39
    Act Density 0.001%

    No Known Activations