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

    Neuronpedia

    INDEX
    Explanations

    201

    np_max-act · gemini-2.0-flash

    references to family activities and bonding experiences.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    นะ
    -0.07
    nh
    -0.06
    uc
    -0.06
    ilo
    -0.06
    _FIELDS
    -0.06
    edges
    -0.06
     wagon
    -0.06
     moh
    -0.06
     bach
    -0.06
    renderer
    -0.06
    POSITIVE LOGITS
    _EST
    0.07
     Trait
    0.07
    _On
    0.06
    ůj
    0.06
     fearless
    0.06
    ('^
    0.06
     зал
    0.06
     vyp
    0.06
    _pas
    0.06
     ARRAY
    0.06
    Act Density 0.035%

    No Known Activations