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

    Neuronpedia

    INDEX
    Explanations

    constructor required parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     உப்பு
    0.43
    olyb
    0.40
    器官
    0.40
    ొప్పి
    0.39
     auricul
    0.39
    innamon
    0.38
    ܘܢ
    0.38
     camin
    0.37
    cohols
    0.37
    μι
    0.37
    POSITIVE LOGITS
     required
    0.84
    required
    0.82
    Required
    0.67
     Key
    0.65
     Required
    0.64
    Key
    0.61
    this
    0.60
    KEY
    0.54
     this
    0.51
    key
    0.51
    Act Density 0.002%

    No Known Activations