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

    Neuronpedia

    INDEX
    Explanations

    references to parts of objects or entities, particularly focusing on "back" and "of" phrases

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

    back of the head

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NgModule
    -0.47
    tonode
    -0.43
     usage
    -0.42
     variety
    -0.40
     example
    -0.38
     offerings
    -0.36
    =()
    -0.36
     offense
    -0.36
     OSError
    -0.36
     illustrazione
    -0.35
    POSITIVE LOGITS
    Back
    0.85
     Back
    0.82
    Behind
    0.80
     BACK
    0.80
    back
    0.79
     BEHIND
    0.79
     Behind
    0.79
     backs
    0.75
    behind
    0.72
     back
    0.72
    Act Density 0.004%

    No Known Activations