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

    Neuronpedia

    INDEX
    Explanations

    increasing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Holiday
    -0.07
     gameplay
    -0.07
    (baseUrl
    -0.07
    浒
    -0.07
    检索
    -0.06
    👶
    -0.06
    𝒂
    -0.06
    Jose
    -0.06
    几百
    -0.06
     infantry
    -0.06
    POSITIVE LOGITS
    	event
    0.08
    chia
    0.07
    ahead
    0.07
     switch
    0.07
    .open
    0.07
    开支
    0.07
     chromat
    0.07
     dlg
    0.07
    ava
    0.07
     modificar
    0.07
    Act Density 0.063%

    No Known Activations