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

    Neuronpedia

    INDEX
    Explanations

    fresh

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of fresh ingredients in recipe or cooking contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ob
    -0.07
     "---
    -0.07
     Plane
    -0.06
    έρει
    -0.06
    hra
    -0.06
     tree
    -0.06
     Walters
    -0.06
     distribution
    -0.06
     utilities
    -0.06
     metres
    -0.06
    POSITIVE LOGITS
     알려
    0.07
    (Fl
    0.07
    ــــ
    0.07
    tier
    0.06
     AUG
    0.06
     fresh
    0.06
    ($(".
    0.06
    ?}",
    0.06
     fleeing
    0.06
    larını
    0.06
    Act Density 0.005%

    No Known Activations