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

    Neuronpedia

    INDEX
    Explanations

    sk

    np_max-act · gemini-2.0-flash

    The neuron predominantly activates on the substring “per-ov-sk-ite,” that is, mentions of perovskite materials.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     property
    -0.06
    _order
    -0.06
    itra
    -0.06
     fluid
    -0.06
    Span
    -0.06
     charisma
    -0.06
     therapy
    -0.06
    .Mon
    -0.06
    Gab
    -0.06
     goodbye
    -0.06
    POSITIVE LOGITS
     pasado
    0.07
    _IMETHOD
    0.06
    mlin
    0.06
    �
    0.06
    Vendor
    0.06
     pushes
    0.06
     forefront
    0.06
     :)
    0.06
    :SetPoint
    0.06
    achel
    0.06
    Act Density 0.001%

    No Known Activations