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

    Neuronpedia

    INDEX
    Explanations

    ent

    np_max-act · gemini-2.0-flash

    This neuron activates on the morpheme “consequent,” i.e. occurrences of the word “consequent” (and its fragmented subparts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .sections
    -0.07
     industrial
    -0.07
     Zion
    -0.06
    inema
    -0.06
     Protein
    -0.06
     goal
    -0.06
    identify
    -0.06
    rewrite
    -0.06
     Ler
    -0.06
     Ağ
    -0.06
    POSITIVE LOGITS
    nee
    0.07
     accompanying
    0.06
    sequent
    0.06
    �
    0.06
    รอบ
    0.06
    +z
    0.06
     fundament
    0.06
    ultimate
    0.06
    질
    0.06
    _gr
    0.06
    Act Density 0.012%

    No Known Activations