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

    Neuronpedia

    INDEX
    Explanations

    rules/instructions

    np_max-act · gemini-2.0-flash

    phrases related to negative or harmful behaviors in relationships.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    یم
    -0.07
    �
    -0.07
    neighbors
    -0.07
     pulls
    -0.07
    ексу
    -0.06
    вают
    -0.06
    __
    -0.06
    ［
    -0.06
     Bewert
    -0.06
    Bit
    -0.06
    POSITIVE LOGITS
     Sơn
    0.06
     susceptibility
    0.06
    .MapFrom
    0.06
    .chart
    0.06
    Dataset
    0.06
    .Sum
    0.05
    (freq
    0.05
     математи
    0.05
     francais
    0.05
    akeFromNib
    0.05
    Act Density 0.084%

    No Known Activations