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

    Neuronpedia

    INDEX
    Explanations

    mental

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stagger
    -0.07
    mts
    -0.07
     spectacular
    -0.07
     mine
    -0.06
     Cities
    -0.06
     Multip
    -0.06
     ấm
    -0.06
     غیر
    -0.05
     mic
    -0.05
     ballots
    -0.05
    POSITIVE LOGITS
    _GROUP
    0.07
    ですか
    0.07
    대한
    0.07
    visející
    0.07
    านคร
    0.06
    Jessica
    0.06
    .stdin
    0.06
    		
↵		
↵
    0.06
    emplate
    0.06
    	RTLU
    0.06
    Act Density 0.012%

    No Known Activations