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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing exclusion or being kept away from something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    out of view or away from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .*")]
    -0.43
    ListItemIcon
    -0.42
     Photocase
    -0.40
    żesz
    -0.39
     Mónica
    -0.38
     Liss
    -0.38
     nakalista
    -0.38
    Espèce
    -0.37
    ationen
    -0.37
    ivably
    -0.37
    POSITIVE LOGITS
     InputDecoration
    0.63
    SequentialGroup
    0.56
    RenderAtEndOf
    0.55
     harm
    0.53
     trouble
    0.53
    __':
    0.48
    ंदीखरीदारी
    0.48
     harms
    0.47
    rrggbb
    0.46
     Harm
    0.44
    Act Density 0.014%

    No Known Activations