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

    Neuronpedia

    INDEX
    Explanations

    mental states and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Przy
    0.74
    「
    0.72
    ീകരിച്ച
    0.72
    wię
    0.70
    change
    0.69
    Change
    0.68
    தியும்
    0.68
    基于
    0.66
    Prés
    0.66
     қол
    0.66
    POSITIVE LOGITS
     mentality
    2.29
     syndrome
    1.94
     Syndrome
    1.71
     tendencies
    1.49
     phenomenon
    1.46
     syndromes
    1.42
     effect
    1.40
     mindset
    1.39
     mantra
    1.37
    效应
    1.34
    Act Density 0.471%

    No Known Activations