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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    passes
    -0.07
     backs
    -0.07
     setting
    -0.06
    Enabled
    -0.06
    _emp
    -0.06
    —a
    -0.06
    `]
    -0.06
    thren
    -0.06
    (w
    -0.06
    >(&
    -0.06
    POSITIVE LOGITS
     this
    0.07
    .game
    0.07
     σχ
    0.07
    ož
    0.06
     staveb
    0.06
     picnic
    0.06
     kararı
    0.06
     Cli
    0.06
     sofort
    0.06
    	this
    0.06
    Act Density 0.039%

    No Known Activations