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

    Neuronpedia

    INDEX
    Explanations

    graphite and clay mixture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     classi
    0.50
    甃
    0.50
    䄱
    0.50
    쐞
    0.48
     listens
    0.47
    椃
    0.47
    ማ
    0.45
     smok
    0.44
     marinas
    0.44
    য়োজনীয়
    0.44
    POSITIVE LOGITS
    anga
    0.50
    ers
    0.49
    گاه
    0.47
    ose
    0.45
    ang
    0.44
    ality
    0.44
    aza
    0.44
    are
    0.44
     Aviation
    0.43
     pasan
    0.43
    Act Density 0.006%

    No Known Activations