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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    The neuron fires on the “Try this…” suggestion phrases that introduce proposed solutions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Yan
    -0.07
     Hair
    -0.06
    oration
    -0.06
    	debug
    -0.05
    าอ
    -0.05
     Tradition
    -0.05
    Choice
    -0.05
    .IGNORE
    -0.05
     harassment
    -0.05
    bands
    -0.05
    POSITIVE LOGITS
    ره
    0.07
    updatedAt
    0.07
    weeks
    0.07
     finished
    0.07
    طفال
    0.07
     wik
    0.07
    gili
    0.07
    pending
    0.07
    /fixtures
    0.07
     "~
    0.07
    Act Density 0.031%

    No Known Activations