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

    Neuronpedia

    INDEX
    Explanations

    actions and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itriangular
    0.50
    iseum
    0.47
    ۰۰
    0.46
    observ
    0.46
    ীম
    0.46
    or
    0.46
     කිරීමට
    0.45
    ig
    0.44
    ast
    0.44
    pm
    0.44
    POSITIVE LOGITS
     nerfs
    0.53
     pneus
    0.50
     bonuses
    0.49
     platelets
    0.49
    \
    0.48
     graphs
    0.47
     vacations
    0.47
     alloys
    0.47
     conjugates
    0.47
     oaks
    0.46
    Act Density 0.001%

    No Known Activations