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

    Neuronpedia

    INDEX
    Explanations

    consent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    .Views
    -0.07
    .guild
    -0.07
    霍
    -0.07
    etections
    -0.06
    ital
    -0.06
    ژه
    -0.06
    prevState
    -0.06
    icrous
    -0.06
    _INITIAL
    -0.06
    POSITIVE LOGITS
    ennes
    0.07
    monic
    0.07
    укт
    0.07
     chic
    0.06
    Applied
    0.06
    	goto
    0.06
    ederation
    0.06
    iggins
    0.06
     अपन
    0.06
     viagra
    0.06
    Act Density 0.041%

    No Known Activations