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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the preposition “into.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    d
    -0.09
    z
    -0.09
    l
    -0.08
    k
    -0.08
    j
    -0.08
    δ
    -0.08
    el
    -0.08
    λ
    -0.08
    b
    -0.07
    w
    -0.07
    POSITIVE LOGITS
     into
    0.20
     Into
    0.18
    Into
    0.14
    _into
    0.12
     onto
    0.11
    into
    0.11
     INTO
    0.11
    .into
    0.11
     In
    0.11
     TO
    0.10
    Act Density 0.079%

    No Known Activations