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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heels
    -0.07
     pře
    -0.07
     Bloss
    -0.07
     pounds
    -0.07
    tearDown
    -0.07
     -->
    -0.06
    ीसर
    -0.06
    오는
    -0.06
    -->
    -0.06
    .Equal
    -0.06
    POSITIVE LOGITS
    Graphic
    0.07
     Dominic
    0.07
     bedding
    0.06
    eriod
    0.06
    _INPUT
    0.06
     liar
    0.06
    Inv
    0.06
    210
    0.06
    	TRACE
    0.06
    alborg
    0.06
    Act Density 0.007%

    No Known Activations