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

    Neuronpedia

    INDEX
    Explanations

    HTTP 400 Bad Request errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Anch
    0.42
     anchors
    0.40
     Nirm
    0.40
     സംഭ
    0.39
     anchor
    0.38
    Anchor
    0.36
    뚫
    0.36
    icher
    0.35
     Nicola
    0.35
     anchoring
    0.35
    POSITIVE LOGITS
     bad
    1.59
    bad
    1.37
    Bad
    1.34
     good
    1.26
     Bad
    1.24
    good
    1.19
    BAD
    1.19
     BAD
    1.17
    悪い
    1.13
     খারাপ
    1.11
    Act Density 0.006%

    No Known Activations