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

    Neuronpedia

    INDEX
    Explanations

    friend

    np_max-act · gemini-2.0-flash

    The neuron fires on terms expressing loyal companionship—words like “friend,” “best friend,” “companion,” and related affectionate descriptors.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     choir
    -0.07
    'It
    -0.07
     δο
    -0.07
     denn
    -0.06
    .file
    -0.06
     تع
    -0.06
    .started
    -0.06
    agas
    -0.06
     heap
    -0.06
    Won
    -0.06
    POSITIVE LOGITS
     Pine
    0.07
     Statistical
    0.07
    Knife
    0.06
     linestyle
    0.06
     substantial
    0.06
     خطر
    0.06
    狠
    0.06
     Whites
    0.06
     Bryce
    0.06
    _inode
    0.06
    Act Density 0.029%

    No Known Activations