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

    Neuronpedia

    INDEX
    Explanations

    along forward

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	items
    -0.08
    .Filter
    -0.06
    /cat
    -0.06
    -API
    -0.06
     xa
    -0.06
    avra
    -0.06
    poser
    -0.06
    _forms
    -0.06
    -making
    -0.06
     który
    -0.06
    POSITIVE LOGITS
     cautious
    0.07
     recognizable
    0.07
    _define
    0.07
     cheered
    0.07
     endeavor
    0.06
     forcefully
    0.06
    •↵↵
    0.06
     громадян
    0.06
     charity
    0.06
    ModifiedDate
    0.06
    Act Density 0.012%

    No Known Activations