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

    Neuronpedia

    INDEX
    Explanations

    introductions

    np_max-act · gemini-2.0-flash

    The neuron responds to formal stage‐announcement phrases—especially lines like “Ladies and Gentlemen, let me introduce you today’s volunteer.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bushes
    -0.07
     Mehr
    -0.07
     discusses
    -0.07
     사라
    -0.06
    _n
    -0.06
     zu
    -0.06
     Comedy
    -0.06
    _smooth
    -0.06
    NE
    -0.06
     ون
    -0.06
    POSITIVE LOGITS
     hung
    0.06
    adaş
    0.06
    nonatomic
    0.06
     kavram
    0.06
    oci
    0.06
    reads
    0.06
    lbrace
    0.06
     �
    0.06
    .ResumeLayout
    0.06
     liquidity
    0.06
    Act Density 0.006%

    No Known Activations