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

    Neuronpedia

    INDEX
    Explanations

    against

    np_max-act · gemini-2.0-flash

    The neuron selectively activates for the preposition “against,” flagging instances of that specific word.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    290
    -0.08
    660
    -0.07
    110
    -0.07
    395
    -0.07
     do
    -0.07
    988
    -0.07
     kode
    -0.07
     lul
    -0.07
     ho
    -0.06
    099
    -0.06
    POSITIVE LOGITS
     against
    0.17
    against
    0.15
     Against
    0.14
    Against
    0.13
     против
    0.08
    UNG
    0.08
    :";
↵
    0.08
     приг
    0.07
    apanese
    0.07
    zens
    0.07
    Act Density 0.028%

    No Known Activations