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

    Neuronpedia

    INDEX
    Explanations

    fallen, dying, damaged states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.68
    is
    0.57
    to
    0.57
     από
    0.55
    ită
    0.55
    it
    0.52
    ंश
    0.51
     ακό
    0.50
     で
    0.49
    besch
    0.49
    POSITIVE LOGITS
    3
    0.64
     toddlers
    0.55
    ದಲ
    0.53
    ми
    0.52
     minors
    0.52
     hordes
    0.52
     young
    0.51
     peppers
    0.50
    6
    0.50
     creatures
    0.49
    Act Density 0.115%

    No Known Activations