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

    Neuronpedia

    INDEX
    Explanations

    wash and washcloths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    タオル
    0.64
     towing
    0.59
     towel
    0.55
     towels
    0.53
     Taurus
    0.52
     dolom
    0.49
     towed
    0.48
     tunnels
    0.48
     towers
    0.47
    鎮
    0.46
    POSITIVE LOGITS
     wash
    0.52
     Wash
    0.50
     TP
    0.47
     apr
    0.45
     face
    0.45
    Beach
    0.45
    Wash
    0.44
     Beach
    0.44
     beach
    0.44
     Paper
    0.42
    Act Density 0.001%

    No Known Activations