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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron detects JavaScript object‐literal property names (especially component option keys like relations, properties, computed, methods, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     流
    -0.07
    ██
    -0.07
    bot
    -0.06
    olid
    -0.06
    ٣
    -0.06
     wires
    -0.06
     gia
    -0.06
    ultip
    -0.06
     Mac
    -0.06
    arius
    -0.06
    POSITIVE LOGITS
    sPid
    0.07
    Alter
    0.06
    arten
    0.06
     lazım
    0.06
    Při
    0.06
     voks
    0.06
     exemplary
    0.06
    Convention
    0.06
    .DataGridViewCellStyle
    0.06
    zend
    0.06
    Act Density 0.008%

    No Known Activations