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

    Neuronpedia

    INDEX
    Explanations

    conclusion or therefore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     buyers
    0.62
     buyer
    0.57
     described
    0.53
     existing
    0.52
     targeted
    0.52
     success
    0.52
     anticipated
    0.51
     beneficiaries
    0.50
     successful
    0.49
     maç
    0.49
    POSITIVE LOGITS
    strokeStyle
    0.58
    เช
    0.54
    شفى
    0.54
    ତା
    0.52
    סף
    0.51
    과학
    0.51
    Grass
    0.51
    Ꮻ
    0.49
    Gather
    0.49
    reinforced
    0.49
    Act Density 0.001%

    No Known Activations