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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    terms related to animal behavior and attributes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     majestic
    -0.07
    via
    -0.07
    яб
    -0.06
     IMapper
    -0.06
     LEN
    -0.06
     brid
    -0.06
     len
    -0.06
     JR
    -0.06
    usat
    -0.06
     Y
    -0.06
    POSITIVE LOGITS
    违
    0.06
    .Components
    0.06
     noop
    0.06
     паци
    0.06
    opts
    0.06
    (__('
    0.06
    '''↵↵
    0.06
    �
    0.06
    .Encoding
    0.06
                ↵            ↵
    0.05
    Act Density 0.009%

    No Known Activations