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

    Neuronpedia

    INDEX
    Explanations

    Bindings

    np_max-act · gemini-2.0-flash

    The neuron activates on the Knockout.js call that applies bindings (i.e. ko.applyBindings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    LastError
    -0.07
    .scheme
    -0.07
    ाहर
    -0.07
    Nearly
    -0.06
    .iteritems
    -0.06
     tranh
    -0.06
    ’h
    -0.06
    Chunk
    -0.06
    Manifest
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     若
    0.07
    Bindings
    0.07
    
    0.06
    _blk
    0.06
    若
    0.06
    ight
    0.06
    .]↵↵
    0.06
    θρώ
    0.06
    camel
    0.06
    osexual
    0.05
    Act Density 0.000%

    No Known Activations