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

    Neuronpedia

    INDEX
    Explanations

    negative situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    άζ
    -0.07
     graphs
    -0.07
     Phase
    -0.07
    ictor
    -0.07
    각
    -0.07
    _TRAN
    -0.07
    ara
    -0.07
     phase
    -0.07
     vase
    -0.07
    uba
    -0.07
    POSITIVE LOGITS
    575
    0.06
    waiting
    0.06
    	break
    0.06
    )';↵
    0.05
    ropdown
    0.05
    >{!!
    0.05
     Mafia
    0.05
     versión
    0.05
     чуть
    0.05
    /");↵
    0.05
    Act Density 0.107%

    No Known Activations