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

    Neuronpedia

    INDEX
    Explanations

    built into readily available components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    прежнему
    0.48
    }${
    0.46
    恢复
    0.46
     .{
    0.45
    }:{
    0.44
     температуре
    0.43
     esfuer
    0.42
    úsica
    0.42
    ,{
    0.41
    েষে
    0.41
    POSITIVE LOGITS
     concret
    0.47
     cryptography
    0.44
     savvy
    0.44
     clandestine
    0.43
     someone
    0.43
     giochi
    0.43
     deductive
    0.43
     concrete
    0.42
     grasping
    0.42
     deductions
    0.42
    Act Density 0.001%

    No Known Activations