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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	msg
    -0.06
    つ
    -0.06
    	conf
    -0.06
     assures
    -0.06
     reasoning
    -0.06
     Harvey
    -0.06
    .pause
    -0.06
     wartime
    -0.06
     Bible
    -0.05
     rituals
    -0.05
    POSITIVE LOGITS
    blo
    0.07
    romium
    0.07
     GER
    0.07
    ेष
    0.07
    >+
    0.07
    _fifo
    0.06
    ]]
↵
    0.06
    อบ
    0.06
     neb
    0.06
    ottle
    0.06
    Act Density 0.050%

    No Known Activations