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

    Neuronpedia

    INDEX
    Explanations

    afterward

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     नॉन
    0.47
     thermometers
    0.47
     maken
    0.46
    æs
    0.46
     échantillons
    0.46
    gå
    0.45
    äche
    0.44
     atteindre
    0.44
    encion
    0.44
     arbres
    0.44
    POSITIVE LOGITS
    ='+
    0.45
    ফুদ্দিন
    0.40
     Statute
    0.39
     vaulted
    0.38
     statue
    0.37
     workstation
    0.37
    0.37
     trab
    0.37
    ;%(
    0.36
     اینکه
    0.36
    Act Density 0.001%

    No Known Activations