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

    Neuronpedia

    INDEX
    Explanations

    list items separated by periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    0.38
     to
    0.32
    ،
    0.31
     ligands
    0.29
     torso
    0.29
     women
    0.29
     invitations
    0.29
    …,
    0.29
     orchids
    0.29
     messengers
    0.28
    POSITIVE LOGITS
    ني
    0.35
    ።
    0.33
     ።
    0.32
     appunto
    0.32
    畱
    0.32
    诨
    0.32
    .³
    0.31
    كي
    0.31
    െടുത്തു
    0.30
    难度
    0.30
    Act Density 2.249%

    No Known Activations