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

    Neuronpedia

    INDEX
    Explanations

    PHP

    np_max-act · gemini-2.0-flash

    The neuron is selectively activated by occurrences of the token “PHP.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     controlling
    -0.08
     odor
    -0.08
     latency
    -0.08
     traces
    -0.07
     strom
    -0.07
     Starr
    -0.07
     tensors
    -0.07
    ozor
    -0.06
     monitored
    -0.06
     Diaz
    -0.06
    POSITIVE LOGITS
     php
    0.11
     PHP
    0.10
    _php
    0.08
    .php
    0.08
    Facebook
    0.08
    /php
    0.07
     PHPUnit
    0.07
     Php
    0.07
    _PHP
    0.07
    PHP
    0.07
    Act Density 0.013%

    No Known Activations