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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron activates on terms naming material‐joining processes—e.g. soldered, brazed, welded, or bonded.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gd
    -0.08
    _shell
    -0.07
     audio
    -0.06
     Invite
    -0.06
    ])+
    -0.06
    eah
    -0.06
    λεκ
    -0.06
     Byte
    -0.06
     appending
    -0.06
    	util
    -0.06
    POSITIVE LOGITS
    _RECEIVED
    0.07
     compil
    0.06
     длитель
    0.06
    ssue
    0.06
    avatars
    0.06
    .JFrame
    0.06
    FirstName
    0.06
     Certificate
    0.06
    ried
    0.06
    NER
    0.06
    Act Density 0.019%

    No Known Activations