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

    Neuronpedia

    INDEX
    Explanations

    Anchor Cemetery, potassium, social safety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ComponentScan
    0.39
    initComponents
    0.38
    GetMapping
    0.37
    cnc
    0.37
    Bug
    0.36
    Il
    0.36
     Damn
    0.35
    rowning
    0.35
    heatmap
    0.35
     Sauber
    0.35
    POSITIVE LOGITS
     Jane
    0.70
    Jane
    0.63
     jane
    0.62
     father
    0.56
     Sp
    0.53
     Molly
    0.49
    father
    0.48
     Father
    0.48
    jane
    0.47
     отца
    0.45
    Act Density 0.000%

    No Known Activations